Digital

This study describes the second iteration of VLEPIC, a gamified and personalised virtual learning environment (VLE) for secondary English students in Ecuador. Adopting a design-based research approach, it focuses on student interaction and system improvement. A mixed-methods design combined survey results, digital logs, and student comments. Results indicated acceptable usability; however, log data showed that platform use was episodic and task-oriented, with no evidence of daily use. Instead, students logged in repeatedly for specific tasks, and participation declined towards the end. Feedback pointed to mobile reading issues, slow loading times, and confusion around task submission. These findings refine design principles (DPs) for schools with limited resources. The resulting priorities are to design for frequent re-entry, simplify task submission, and present progress more clearly. Together, these DPs offer practical guidance for VLEs in such settings. They illustrate how design can support continuity, reduce uncertainty, and sustain learning routines when access is interrupted. Full article

Ecuador’s agricultural sector plays a strategic role in the national economy; however, agricultural data remains fragmented across heterogeneous and isolated sources, limiting integrated analysis and evidence-based decision-making. This study proposes and implements a Big Data analytics framework based on the Medallion architecture and interactive dashboards to integrate, process, and visualize agricultural indicators from INEC, ESPAC, Ecuador Open Data, and FAOSTAT for the 2010–2024 period. The proposed framework adopts the Team Data Science Process (TDSP) methodology and structures workflows into Bronze, Silver, and Gold layers using Databricks for scalable data ingestion, transformation, and dimensional modeling. Interactive dashboards were developed in Tableau Public to support dynamic analysis of agricultural production, trade, producer prices, losses, and producer profiles. A comparative performance evaluation between Databricks Free Edition and Azure Databricks was conducted using SQL analytical workloads and dashboard interaction tests. Results showed that Azure Databricks reduced query execution times by up to 57%, especially in aggregation and join operations. Usability validation with 31 agricultural stakeholders reported high acceptance levels, including a 100% recommendation rate and a data trust score of 4.45/5. The findings demonstrate that scalable and low-cost Big Data technologies can effectively support agricultural digital transformation. Full article

Deep Neural Networks (DNNs) are increasingly being used in the design of industrial safety-critical autonomous applications such as autonomous vehicles, industrial robotics, and medical instrumentation and control systems. Ensuring reliable and robust operation of the DNN-based safety-critical systems is challenging because of the complex structure of DNN hardware accelerators utilized for inference that are susceptible to the effects of multi-faults, common-cause fault models, data uncertainties, and unpredictable erroneous behavior. Additionally, transient, permanent, and timing faults affect the accelerator design of processing elements, memory arrays, and datapaths, propagate through DNN computations, and potentially can cause catastrophic failures at the system level. The objective of this survey paper is to systematically evaluate the state-of-the-art fault-tolerant DNN accelerator architectures with particular emphasis on their applicability to safety-critical autonomous systems in industry. The survey investigates architectural perspective, fault modeling, and platform-level trade-offs, runtime resilience, validation practices, and certification readiness, following a PRISMA methodology with evidence-driven synthesis and unbiased study selection. Database searches across IEEE Xplore, Scopus, and Web of Science identified 200 records, of which 82 studies were included based on predefined inclusion and exclusion criteria emphasizing industrial safety-critical relevance, fault modeling at the hardware level, and the implementation at the architectural level. The results indicate that there was a clear shift from traditional redundancy-based approaches to cross-layer and adaptive approaches that provide better trade-offs between performance, reliability, and hardware overhead. The current studies presented are based on simplified fault models, incomplete validation- procedures, and limited consideration of system-level and certification needs, which often do not consider critical failure modes such as Silent Data Corruption (SDC). This has resulted in a significant gap between research-level solutions and industrial deployment requirements. This survey underscores the need for scalable, integrated, and certification-aware design approaches to help connect fault modeling, architectural resilience, validation, and safety assurance to develop reliable and deployable DNN accelerator systems for next-generation industrial safety-critical autonomous applications. Full article

Digital twin (DT) technology has expanded far beyond its industrial origins, increasingly finding application across environmental and territorial domains. This review provides a structured mapping of DT deployments at environmental and territorial scales over the period 2020–2025, examining 117 peer-reviewed publications (109 applied studies and 8 review articles) through a structured 16-parameter classification framework. The review traces three major conceptual shifts in the DT paradigm: from industrial assets to living entities, from discrete systems to Earth-scale representations, and from closed deterministic models to ecological and systemic frameworks, as reflected in the emergence of ecological digital twins (EcoDTs), environmental digital twins (EDTs), and territorial digital twin (TDT) definitions. The results reveal a clear growth trajectory in DT applications across themes, with urban systems as the most consolidated application domain, and progressive diversification into marine, coastal, forestry, river/lake, and Earth system applications from 2022 onward. Institutional actors dominate production in this space, aligned with European flagship initiatives such as Destination Earth (DestinE) and the European Digital Twin of the Ocean (EDITO). The findings position and expand the notion of territorial digital twins as an evolving paradigm, underscoring both the momentum generated by EU digital and environmental policy and the need for integrated tools to answer and respond to key environmental challenges. Full article

Traditional dementia care training often falls short in equipping staff with the knowledge and skills needed to improve quality of life for people with dementia. Virtual Reality (VR)-based experiential learning has emerged as a promising approach, enhancing learning outcomes and training experience for individuals receiving education and training related to dementia care. This scoping review mapped VR education tools used in dementia care, the UX-related measurement methods employed, and the extent to which UX design has been integrated into these tools. Guided by Arksey and O’Malley’s framework, a systematic search was conducted across seven databases (Scopus, Web of Science, ProQuest, MEDLINE, CINAHL, IEEE Xplore, PubMed). PRISMA ScR guidelines were used to map gaps in UX design and engagement strategies within VR learning systems. Data were extracted using a comprehensive UX framework for immersive VR to synthesize user experience components. Twenty-four peer-reviewed publications were included, covering VR scenario development and UX. The findings suggest potential benefits of integrating UX principles into VR education tools to support training experience, learner satisfaction, and care quality. A key gap was identified: limited and inconsistent integration of UX design components and measurement methods within existing VR tools. Drawing on these insights, the review provides practical guidance for optimizing VR training programs in dementia care. Full article

In today’s manufacturing industry, work-related musculoskeletal disorders (WMSDs) remain among the most prevalent occupational health issues. Collaborative robots (cobots) represent a promising technology to address this challenge. Consequently, ergonomics assessment in human–robot collaboration (HRC) has gained increasing attention in recent years. This study investigates the feasibility of using a coupled digital twin system consisting of a digital human model (DHM) and a cobot digital twin to assess detailed ergonomic parameters such as muscle activations and joint reaction forces in an HRC task. Selected parameters are used to develop an ergonomics map that condenses the effects of human–robot interaction into a single scalar value for each working position in the coronal plane in front of the user. The ergonomics mapping approach is presented, key influencing factors are identified, and critical workspace design implications are discussed. Full article

In today’s educational context, Game-Based Learning (GBL) has emerged as a promising methodology for promoting active learning in an engaging and motivating way. This study aims to analyze the impact of a video game-based intervention on the development of students’ cognitive skills, focusing on the levels of Bloom’s taxonomy, as well as to explore students’ perceptions of this methodology. Accordingly, an intervention was conducted with 52 students in the Early Childhood Education Degree Program, integrating video games designed for this study for pedagogical purposes. An approach combining two quantitative instruments was employed: knowledge assessment tests and a student perception questionnaire. The results show a significant improvement in students’ higher-order cognitive skills, particularly in the dimensions of applying, analyzing, and evaluating. Furthermore, students demonstrated a positive attitude toward the use of video games as a learning tool. Therefore, this study confirms that the integration of GBL methodology at the university level can effectively contribute to the development of higher-order cognitive skills among teachers in initial training. However, further research is recommended to examine its long-term impact and its effectiveness across different levels of education. Full article

Reliable delineation of brain tumor boundaries in multimodal magnetic resonance imaging (MRI) remains challenging despite substantial advances in deep learning–based segmentation. Although modern encoder–decoder architectures achieve strong volumetric overlap, precise geometric alignment of tumor contours remains inconsistent, particularly for small lesions and heterogeneous clinical cases. In neuro-oncology, even minor boundary deviations may influence surgical planning, radiotherapy targeting, and longitudinal treatment assessment. These limitations suggest that segmentation performance is not determined solely by network depth or loss design, but also by how multimodal information is structured prior to learning. We introduce CMYD-SurfaceNet, a scale-aware cascaded framework that restructures multimodal MRI inputs at the representation level to enhance boundary-sensitive segmentation. Rather than treating modalities as independently concatenated channels, selected sequences are first organized into a task-guided pseudo-RGB projection. This intermediate representation is subsequently transformed into the CMYK color space to disentangle shared luminance structure from modality-specific contrast dominance. To further encode geometric priors, a gradient-derived boundary density channel is incorporated to explicitly emphasize spatial discontinuities corresponding to tumor margins. The resulting CMYD representation is integrated within a two-stage nnU-Net cascade, where global tumor localization is followed by high-resolution region-of-interest refinement with auxiliary contour supervision. This scale-aware design improves sensitivity to small tumor components while stabilizing contour delineation. Extensive evaluation on the BraTS benchmark demonstrates consistent improvements in boundary-sensitive metrics. Compared with baseline nnU-Net, the proposed framework reduces HD95 from 3.6 mm to 2.4 mm and increases Surface Dice at 1 mm tolerance from 0.82 to 0.89, while maintaining competitive Dice performance. These findings suggest that representation-level structural decoupling, when combined with scale-aware refinement, may provide clinically relevant boundary-aware multimodal MRI segmentation support without increasing architectural complexity. Full article

This study aims to investigate the integration of generative artificial intelligence (GAI) and advanced large language models (LLMs) in financial sentiment research, focusing on improving the accuracy and robustness of financial sentiment classification from investor-generated textual data. The research employs advanced large language models, including XLNet, FinBERT, T5, Gemma-7B, Llama-2, and Llama-3, specifically fine-tuned to address the intricacies of financial language. We utilize generative AI models, such as GPT-4, GPT-3.5, and GPT-2, for data augmentation to mitigate scarcity. The fine-tuned Gemma-7b model proved to be the most successful, with a greater Success Rate (S-rate). The Gemma-7b model showed significant enhancements in performance after fine-tuning, highlighting its capacity to grasp the intricacies of financial emotion. This methodology provides a robust framework for financial sentiment classification and supports the extraction of meaningful sentiment signals from financial text. The results demonstrate the effectiveness of advanced LLMs for financial sentiment analysis and highlight their potential for supporting future research and analytical applications in financial text mining. Full article

The rapid advancement of information technology and multimedia applications has led to an increasing demand for video data processing. In particular, video fusion technology in multi-camera environments, which integrates and optimizes video data from multiple camera viewpoints, plays a crucial role in enhancing visual quality and improving the completeness of information. This technology addresses the challenge of obtaining high-quality video content in complex and dynamic environments. By improving image clarity, expanding perspective information, and enhancing scene understanding, video fusion technology has shown significant potential for a wide range of applications, attracting considerable attention from both academia and industry. Despite the existence of several review articles on video fusion, they tend to focus on isolated aspects of the technology and often lack a comprehensive, systematic overview of the field. To fill this gap, this paper provides an in-depth review of the research on video fusion technology in multi-camera scenarios. The paper covers the definition of video fusion; offers a detailed classification of key technologies, such as geometric correction and alignment, perspective fusion, spatio-temporal fusion, and multi-modal fusion; and explores its applications in diverse fields including surveillance security, virtual reality, film and television production, intelligent transportation, medical imaging, robotics, and unmanned aerial vehicles. Additionally, the paper examines the role of edge caching in video fusion, highlights the current challenges faced by the field, and discusses the potential of video fusion technology for driving innovation across multiple industries. Full article

Digital resilience has become an increasingly important concept in information systems research due to growing dependence on digital infrastructures, escalating cyber threats, and the emergence of regulatory frameworks that formalize resilience obligations. This study provides a systematic literature review of how digital resilience is conceptualized, operationalized, and aligned with emerging European Union (EU) regulatory frameworks. Following PRISMA 2020 guidelines, a systematic search was conducted across Scopus, Web of Science, and IEEE Xplore databases. Fifty-three peer-reviewed studies published between 2006 and 2026 were analyzed using a structured analytical coding framework capturing conceptual clarity, dimensional structure, methodological maturity, and regulatory alignment. The results reveal significant conceptual fragmentation across the literature. While governance, ICT risk management, incident response, and third-party risk management emerge as recurring resilience dimensions, definitional and structural convergence remains limited. Measurement approaches are dominated by maturity models and qualitative assessment frameworks, with relatively few studies proposing validated indicator-based models. Regulatory alignment with EU frameworks such as the Digital Operational Resilience Act (DORA) and the Network and Information Security Directive (NIS2) remains partial and inconsistent. The study identifies a structural alignment gap between regulatory resilience requirements, conceptual resilience models, and operational measurement approaches, providing a foundation for developing regulator-compatible digital resilience assessment frameworks. Full article

Pipelines remain the primary mode of oil and gas transportation but are vulnerable to leaks that pose environmental and safety risks, particularly in two-phase flow systems. Conventional detection methods often struggle under transient multiphase conditions, while many data-driven studies rely on static evaluation metrics that do not reflect continuous monitoring requirements. This study develops a machine learning framework for leak detection using OLGA-simulated datasets from a previously published study, comprising approximately 180,000 labelled samples across nine leak scenarios and one no-leak case. Pressure, temperature, and mass-flow variables were enhanced through feature engineering to capture nonlinear leak behaviour. Random forest and extreme gradient boosting (XGBoost) classifiers were trained using an 80/20 stratified split with synthetic minority oversampling technique (SMOTE)-based balancing applied only to training data. XGBoost achieved 99.2% accuracy and reduced false positives by 53% relative to random forest while maintaining near-zero false negatives. A sliding-window suspicion framework extended static classification into time-dependent detection, producing delays of between 9.81 s and 82.04 s with zero false alarms in the no-leak scenario. Physical validation using pressure, flow, and fast Fourier transform (FFT) analysis confirmed that detections correspond to genuine hydraulic disturbances, demonstrating the reliability and physical credibility of the proposed framework. Full article

With the rapid growth of edge computing applications, optimizing both edge server placement and task offloading decisions is critical for minimizing system latency in edge–cloud environments. However, these two problems are tightly coupled and jointly form a binary non-linear programming (BNLP) problem that is NP-hard. To address this challenge, this paper proposes a novel hybrid meta-heuristic algorithm with alternating iteration, which decouples the joint optimization into two interdependent subproblems: edge server placement and task offloading. These subproblems are solved alternately using particle swarm optimization (PSO) for placement and a genetic algorithm (GA) for offloading, respectively. PSO efficiently explores the discrete placement space under bound constraints, while GA effectively navigates the high-dimensional binary offloading space. Compact encoding schemes are designed to inherently satisfy problem constraints, reducing search overhead and improving convergence. The overall algorithm exhibits polynomial-time complexity, making it scalable for practical deployments. Extensive experiments comparing the proposed method against ten baseline algorithms demonstrate that it achieves the best latency with the smallest standard deviation. The results validate the effectiveness, robustness, and scalability of the proposed alternating iterative hybrid meta-heuristic approach for joint edge server placement and task offloading optimization. Full article

Digital Product Passports (DPPs) are being introduced in the European Union to support circular economy strategies, improve product transparency, and enable lifecycle-based compliance and decision-making. Despite growing interest, research on DPPs remains fragmented, and there is limited consensus on how to design and validate DPP frameworks in real-world contexts. This paper presents a systematic literature review of peer-reviewed studies that explicitly define, structure, or assess DPP-related frameworks. Using a transparent search strategy based on Scopus and IEEE Xplore, combined with structured screening, the review assesses framework design elaboration and validation maturity across included studies and interprets recurring framework archetypes across application sectors. The results show that most studies emphasise conceptual or architectural designs. These commonly adopt data-centric, layered, technology-anchored, or ecosystem-oriented structures and frequently refer to enabling technologies such as digital twins, blockchain, data spaces, and knowledge graphs. However, explicit validation remains limited and is primarily restricted to illustrative case studies, stakeholder-informed assessments, or prototypes, with few studies evaluating scalability, interoperability, or lifecycle-spanning operation in real-world contexts. By consolidating design principles and validation practices across sectors in this targeted corpus, the review clarifies the current state of the art and highlights critical research gaps. The findings indicate that DPP research is characterised by a strong emphasis on framework design, with comparatively limited empirical validation. Furthermore, critical research gaps include the lack of rigorous empirical validation, cross-organisational testing, lifecycle-spanning evaluation, clearly defined data governance responsibilities, convergence towards shared reference architectures, and sector-specific adaptation. Full article

Employee attrition presents a significant threat to organizational continuity, as frequent turnover depletes valuable intellectual capital and incurs heavy recruitment costs. Although ensemble machine learning models often achieve high accuracy in predicting employee departure, they tend to generalize poorly and yield poorly calibrated probability estimates. In high-stakes human resources (HR) decision-making, miscalibrated models produce overconfident or underconfident risk scores that do not reflect true exit likelihoods, leading to suboptimal intervention strategies and resource misallocation. This paper proposes a unified approach combining a Gradient Boosting classifier with post hoc temperature scaling, to meet the dual needs of prediction strength and reliability. Experiments show that the proposed approach consistently improves probability calibration across all datasets; however, on the local dataset, the underlying predictive signal remains weak, so the resulting risk scores should be interpreted as modestly informative rather than strongly discriminative. Comparative scores with other calibration methods are also presented. The study underscores that well-calibrated risk scores are crucial for converting predictive outputs into actionable insights, allowing quantitative analysis to effectively support human judgment in workforce planning. Full article

The rapid proliferation of Internet of Things (IoT) devices has dramatically expanded the attack surface for cyber threats, exposing critical infrastructure to sophisticated intrusion attempts that traditional static intrusion detection systems (IDS) fail to counter effectively. This paper proposes an autonomous reinforcement learning (RL)-based IDS framework for dynamic IoT networks, capable of adaptive, real-time threat detection without human intervention. The proposed system integrates a Deep Q-Network (DQN) agent with a hybrid convolutional neural network–long short-term memory (CNN-LSTM) feature extractor to identify and classify malicious network traffic across 33 attack categories. We evaluate the framework on two recent, publicly available benchmark datasets: CICIoT2023, comprising 8.94 GB of traffic from 105 real IoT devices, and CIC IoT-DIAD 2024, a flow-based dataset with diverse attack and benign scenarios. Experimental results demonstrate superior detection performance compared to baseline classifiers, including SVM, Random Forest, and standalone deep learning models, with improved F1-score, reduced false alarm rate (FAR), and lower detection latency. The reward-shaping strategy explicitly penalizes false positives, addressing a key limitation of prior RL-based IDS approaches. This work contributes a scalable, dataset-agnostic autonomous defense architecture suitable for real-world IoT deployment. Full article

Children increasingly consume online video content, creating a growing need for scalable approaches to support content moderation workflows. However, directly identifying harmful or policy-violating content, such as violence, sexual content, or self-harm, remains a complex task that typically requires specialized classifiers and domain-specific annotations. In this context, sentiment analysis can provide complementary information by capturing affective signals expressed through language and visual cues. This study does not treat sentiment polarity as a direct indicator of unsafe or policy-violating content. Instead, it explores multimodal sentiment analysis as an auxiliary triage signal that may help prioritize content for human review or identify segments requiring further inspection. This paper investigates the feasibility of using large vision–language models (LVLMs) for zero-shot multimodal sentiment analysis on utterance-aligned video segments. We evaluate two LVLMs, LLaVA-OneVision-7B and Qwen2.5-VL-7B, under three input settings: text-only, vision-only, and multimodal, using a conversational TV-series dataset consisting of short utterance-level video segments and transcripts. The results show that multimodal sentiment inference can provide useful screening signals without task-specific fine-tuning, although the benefits are model-dependent. LLaVA-OneVision-7B consistently outperforms Qwen2.5-VL-7B and benefits more clearly from combining textual and visual inputs, whereas Qwen2.5-VL-7B shows limited improvement across modality settings. We also analyze the trade-off between frame sampling and image resolution. Finally, we discuss limitations related to dataset scope, annotation subjectivity, class imbalance, and the need for broader validation before real-world deployment. Full article

Manual assembly remains critical in Industry 5.0 high-mix/low-volume manufacturing, but it introduces resilience challenges due to cognitive load, training demands and frequent product changes. While AI-based supervision can mitigate errors, deploying such systems is often hindered by the cost of collecting and labelling thousands of real images for each product variant. This paper presents a Human-in-the-Loop semantic-twin pipeline that generates approximately 45,000 labelled synthetic images from a single CAD-based configuration and uses them to train an object detection model for real-time assembly supervision. Experiments on seven virtual environment configurations show that removing realistic lighting or camera motion reduces F1-score on real images from 0.87 to 0.46, confirming their critical role for synthetic-to-real transfer. A controlled laboratory study on a single bicycle chainring assembly task with 10 participants and 100 monitored cycles demonstrates the feasibility of automatic KPI extraction, with error events associated with a 25.6% increase in average cycle time (from 58.4 s to 73.3 s) under the tested conditions. Compared to manual annotation, where labelling 3000 images required approximately 4 h, the semantic-twin configuration takes around 4 to 6 h including image generation that enables rapid creation of large labelled datasets for new product variants without additional human annotation. These results provide a proof-of-concept foundation for resilient, data-efficient supervision of high-mix manual workstations, with full industrial validation across multiple products, stations and operator demographics identified as the necessary next step. Full article

In recent years, increasing attention has been paid to the effects of reading and art on the human brain. However, how these activities are associated with brain structure in healthy middle-aged adults remains unclear, partly because structural brain measures are not easily accessible outside MRI-based settings. In Study I, we analyzed the correspondence between gray matter volume (GMV) derived from brain MRI and facial-expression data obtained while participants imitated four facial expressions (happiness, anger, sadness, and surprise). Based on these data, we developed an exploratory algorithm and a digital application to estimate brain-health-related indices from facial expressions. In Study II, we examined correlations between the estimated brain-health-related indices and questionnaire-based measures of creative behavior and reading habits in 113 self-reported healthy middle-aged adults. The results showed that estimated indices related to the default mode network (DMN) and central executive network (CEN) were positively associated with creative behavior and reading habits, respectively. To our knowledge, this is among the first studies to explore whether facial-expression-based estimates of brain-health-related indices may be used to examine associations between everyday intellectual activities and brain-health-related characteristics. However, the findings should be interpreted cautiously because the estimation model was evaluated within a limited sample, included repeated observations, and has not yet been externally validated. Full article